Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1867. Min Range: -10.1867
Max Act: 10.1867. Min Act: -0.1700
Data Index: 2137782 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.7492. Min Act: -0.1700
Data Index: 2158061 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3742. Min Act: -0.1700
Data Index: 4372013 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3742. Min Act: -0.1700
Data Index: 762855 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.4367. Min Act: -0.1700
Data Index: 1076011 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3742. Min Act: -0.1700
Data Index: 847014 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3742. Min Act: -0.1700
Data Index: 8030618 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3742. Min Act: -0.1700
Data Index: 156338 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3117. Min Act: -0.1700
Data Index: 2661969 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3117. Min Act: -0.1700
Data Index: 6757110 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.2492. Min Act: -0.1700
Data Index: 3113438 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.3117. Min Act: -0.1700
Data Index: 2480729 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.2492. Min Act: -0.1700
Data Index: 4318234 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.2492. Min Act: -0.1700
Data Index: 1355870 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.1867. Min Act: -0.1700
Data Index: 2409014 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.1242. Min Act: -0.1700
Data Index: 8545123 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.1242. Min Act: -0.1700
Data Index: 3157270 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.1867. Min Act: -0.1700
Data Index: 6346305 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1867. Min Range: -10.1867
Max Act: 9.0617. Min Act: -0.1700
Data Index: 1784326 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1867. Min Range: -10.1867
Max Act: 8.9992. Min Act: -0.1700
Data Index: 2472133 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19